Search Results

K5 is intended to supply power to and serve as a base for dental devices and accessories. This product is intended for use by dentist and dental assistance to assist dental treatment of patients for adjusting the position of the patient seat, operating the instruments, and supplying water into the oral cavity through a water line in dental clinical environments.

The K5 Cart, K5 Mount and K5 Swing are designed for dental treatment and are intended for dental use only and are intended for use by trained medical personnel only.

These devices consist of a foot controller, headrest, backrest, seat, armrest, doctor table, unit, dental light, auxiliary table and doctor stool.

These are an AC-powered dental operative unit with accessories, intended to supply power to and serve as a base for other dental devices. It includes a treatment chair, dentist element, assistant element and a dental light as offering several additional options and electronically-controlled chair movements with software and water unit functions.

The provided FDA 510(k) clearance letter and summary for the K5 Cart, K5 Mount, K5 Swing devices (K251491) indicate that these devices are Class I Dental Operative Units and Accessories. Class I devices are generally considered to be low-risk and often demonstrate substantial equivalence through non-clinical testing rather than extensive clinical studies.

The document extensively compares the proposed devices to a predicate device (K5, K233805) to establish substantial equivalence. It does not describe specific acceptance criteria in terms of performance metrics with numerical thresholds for the device's function as a whole. Instead, it relies on compliance with recognized consensus standards and a detailed comparison of technological characteristics.

Therefore, many of the requested details about acceptance criteria for device performance (e.g., accuracy, sensitivity, specificity, or improvement over human readers) are not applicable or not explicitly stated in this type of 510(k) submission for a Class I mechanical device. The "acceptance criteria" here are primarily met by demonstrating compliance with safety and performance standards relevant to dental operative units and showing that any differences from the predicate device do not raise new questions of safety or effectiveness.

Here's an analysis based on the provided document, addressing the points where information is available and noting where it's not applicable for this type of device and submission.

Acceptance Criteria and Device Performance

As a Class I dental operative unit, the "acceptance criteria" are primarily established by compliance with recognized electrical safety, electromagnetic compatibility, and performance standards for dental equipment, along with demonstrating that any differences from a predicate device do not introduce new safety or effectiveness concerns. The performance is assessed qualitatively through compliance with these standards and by direct comparison of functionalities and specifications with the predicate device.

Table of Acceptance Criteria and Reported Device Performance

Study Details

It's important to differentiate that this 510(k) submission is for a mechanical/electrical dental operative unit, not an AI/software as a medical device (SaMD). Therefore, many of the questions related to AI performance metrics, clinical study design for accuracy/sensitivity, expert readers, and ground truth establishment (common for imaging AI) do not apply to this clearance. The "study" here is primarily a series of non-clinical tests and a detailed comparison to a predicate device.

1. Sample sizes used for the test set and the data provenance:

• Test Set Sample Size: Not applicable in the context of typical AI/imaging studies. Performance was demonstrated through compliance with recognized standards (IEC 60601-1, IEC 60601-1-2, IEC 80601-2-60, IEC 60601-1-6, ISO 7494-1, ISO 7494-2) and direct engineering measurements and comparisons. This involved testing the physical device(s).
• Data Provenance: Not applicable in the sense of patient data. The testing involves engineering and safety evaluations of the manufactured devices.

2. Number of experts used to establish the ground truth for the test set and the qualifications of those experts:

• Not applicable. The device is a dental operative unit, not an AI diagnostic tool requiring expert-established ground truth from medical images. Compliance with engineering standards and functional specifications constitutes the "ground truth" for this device type.

3. Adjudication method (e.g., 2+1, 3+1, none) for the test set:

• Not applicable. This is not a study involving human reader adjudication of diagnostic outputs.

4. If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

• Not applicable. This is not an AI diagnostic or assistive device for human readers.

5. If a standalone (i.e., algorithm only without human-in-the-loop performance) was done:

• Not applicable, as it's not an algorithm-based device in the diagnostic sense. The device performs its intended functions independently (e.g., moving chair, supplying water/air, powering instruments).

6. The type of ground truth used (expert consensus, pathology, outcomes data, etc.):

• For this device, "ground truth" is established by:
  • Compliance with recognized consensus standards: e.g., IEC 60601-1 (Electrical Safety), IEC 60601-1-2 (EMC), ISO 7494-1 (Dental Units), ISO 7494-2 (Dental Chairs).
  • Engineering specifications and measurements: Verifying that the device meets its design specifications for things like air pressure, water pressure, chair movement ranges, and patient load.

7. The sample size for the training set:

• Not applicable. This is not a machine learning/AI device requiring a training set.

8. How the ground truth for the training set was established:

• Not applicable. No training set is used.

Ask a specific question about this device

The system is intended to be used by a trained/qualified healthcare professional in a hospital or clinical setting for ultrasound evaluation of fetal, abdominal, pediatric, small organ (thyroid, testes, breast), neonatal cephalic, musculoskeletal (conventional and superficial), cardiac (adult and pediatric), liver, peripheral vascular, trans-vaginal, trans-rectal, obstetrics/ gynecology applications in B-Mode(B, 2B, 4B), M-Mode, Anatomical M-mode, Color M, Color Flow Map (CFM), Power Doppler Imaging (PDI), Directional Power Doppler Imaging (DPDI), Pulsed Wave Doppler (PWD), Continuous Wave Doppler(CWD), 3D/4D, Elastography, Contrast Harmonic Imaging(CHI), S-Beam, Panoscope, Trapezoidal/Extended Sector Imaging, Tissue Doppler Imaging(TDD), Tissue Harmonic Imaging(THI), Macro Fidelity Imaging(MFI), ECG, Vector Space Flow (VS Flow), DICOM.

This system is a Track 3 device and the software used in Apogee C1, Apogee C2, Apogee C3, Apogee C5, Apogee K1, Apogee K2, Apogee K3, Apogee K5, Apogee U1, Apogee U2, Apogee U3, Apogee U5 Digital Color Ultrasound Imaging System is Ultrasound Software by SIUI and is based on the predicate device. The Document Level for the Ultrasound Software is Basic.

Here's a breakdown of the acceptance criteria and study information based on the provided text:

Important Note: The provided document is a 510(k) summary for an ultrasound system. It primarily focuses on demonstrating substantial equivalence to a predicate device based on technical characteristics, safety standards, and intended use. It explicitly states that clinical testing was not necessary to demonstrate substantial equivalence. Therefore, many of the requested items related to a clinical study (like test set sample size, expert qualifications, adjudication methods, MRMC studies, or standalone performance for an AI algorithm) are not applicable to this submission.

The document discusses non-clinical testing related to compliance with various international standards for medical electrical equipment, software, biocompatibility, and risk management. This type of testing ensures the device meets safety and performance criteria, but it's not a performance study in the sense of evaluating diagnostic accuracy against a ground truth for a specific clinical application.

1. Table of acceptance criteria and the reported device performance

Since this is a substantial equivalence claim for an ultrasound system, the acceptance criteria are primarily based on meeting safety standards and demonstrating comparable technical characteristics and intended use to the predicate device. There isn't a table of specific performance metrics for clinical accuracy as would be found in a study for an AI-powered diagnostic device.

• IEC 60601-1 (Basic safety & essential performance)
• IEC 60601-1-2 (EMC)
• IEC 60601-2-37 (Ultrasonic diagnostic & monitoring equipment)
• IEC 60601-2-25 (Electrocardiographs)
• ISO 14971 (Risk management)
• ISO 10993 (Biocompatibility parts 1, 5, 10, 23)
• IEC 62304 (Software life cycle)
• IEC 60601-1-6 (Usability)
• IEC 62366-1 (Usability engineering)
• ISO 15223-1 (Symbols for labels)
• ISO 13485 (Quality management systems)
• FDA Guidance for PMS for Software in Medical Devices
• Marketing Clearance of Diagnostic Ultrasound Systems and Transducers |
  | Software Document Level | Software documentation should meet the basic document level requirements, indicating proper development and verification processes. | "The Document Level for the Ultrasound Software is Basic." |

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)

• Not Applicable. The document explicitly states: "Clinical testing is not necessary for the Apogee C2... Digital Color Doppler Ultrasound Imaging System in order to demonstrate substantial equivalence to the predicate device." Therefore, there was no clinical test set in the traditional sense of a performance study to evaluate diagnostic accuracy. The "test set" for this submission refers to the physical device being tested against safety and performance standards, and comparison of its specifications to the predicate device.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)

• Not Applicable. As explained above, no clinical test set requiring expert-established ground truth was part of this 510(k) submission.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set

• Not Applicable. No clinical test set with adjudication was part of this 510(k) submission.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance

• No. This submission is for a general-purpose ultrasound imaging system, not an AI-assisted diagnostic tool. No MRMC study was conducted or reported.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done

• No. This submission is for an ultrasound imaging system. It states the software is "Ultrasound Software by SIUI" and is "based on the predicate device." It does not describe a standalone AI algorithm for diagnostic interpretation.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)

• Not Applicable. For the non-clinical testing performed (compliance with standards), the "ground truth" is adherence to the specifications of those standards (e.g., electrical safety limits, EMC performance, software lifecycle processes) and comparison of technical parameters to the predicate device. There was no clinical ground truth established for diagnostic performance.

8. The sample size for the training set

• Not Applicable. This submission does not describe an AI/machine learning model that would require a training set of patient data. The "software" referred to is the operating system and imaging processing software of the ultrasound machine, not a data-driven AI algorithm in the diagnostic sense implied by this question.

9. How the ground truth for the training set was established

• Not Applicable. As no training set was used, no ground truth needed to be established for it.

Ask a specific question about this device

Wearable Breast Pump (ABP-1508PRO, ABP-1306, ABP-1306, ABP-1306 PRO, M1, M3, M8, M5, M6, K1, K2, K3, K5, ABP-1306PLUS, ABP-1308, M2) is a powered breast pump to be used by lactating women to express and collect milk from their breasts. The device is intended for a single user.

The Wearable Breast Pump (ABP-1508PRO, ABP-1506, ABP-1306 PRO, M1, M3, M8, M5, M6, K1, K2, K3, K5, ABP-1306PLUS, ABP-1308, M2) is an electrically powered breast pump to be used in a home environment by a single user. The device is provided non-sterile and can be used on one breast (single pumping) or on both breasts at the same time (double pumping). The subject devices are capable of expression, stimulation, and auto modes with nine associated suction levels for each. The subject devices feature various combinations of on/off buttons, level up/down buttons, mode selection buttons, suction level/time indicators, battery visual indicator displays. The pumps are powered by internal, non-replaceable, rechargeable lithium-ion batteries which are charged using the included AC power supply and cable. The subject device can be operated while plugged into AC power. The breast pumps use cyclic negative pressure (suction) to mimic the suckling patterns of a feeding infant. A DC motor drives a membrane vacuum pump to generate the suction required to stimulate and express breast milk. The timing of this pattern is dependent upon the suction/speed settings selected by the user and is preprogrammed in the devices. The devices are capable of producing peak suction levels between -60 and -240 mmHg at speeds between 26 and 108 cycles per minute. There available pumping modes with 9 distinct levels of vacuum and cycle speed. The subject device ensures backflow protection between the breast shield and the electronic components via a physical barrier (silicone diaphragm) mechanism. All other components (i.e., motor unit) of the subject device are not in contact with the breast. All milk contacting components are compliant with 21 CFR 174-179.

The provided text describes a 510(k) premarket notification for a Wearable Breast Pump and does not include information about a study that proves the device meets specific acceptance criteria for AI/ML performance. The document focuses on demonstrating substantial equivalence to a predicate device through non-clinical performance testing.

Therefore, I cannot provide the requested information regarding:

• A table of acceptance criteria and reported device performance for AI/ML.
• Sample size and data provenance for a test set.
• Number and qualifications of experts for ground truth establishment.
• Adjudication method for a test set.
• Whether a multi-reader multi-case (MRMC) comparative effectiveness study was done, or its effect size.
• Whether a standalone (algorithm only) performance study was done.
• The type of ground truth used (expert consensus, pathology, outcomes data, etc.).
• The sample size for the training set.
• How the ground truth for the training set was established.

The document mentions "Software" and states it was "evaluated at the Basic Documentation level as recommended in the 2023 FDA guidance document 'Content of Premarket Submissions for Device Software Functions.'" This level of documentation suggests that the software in question is likely not an AI/ML algorithm that requires rigorous clinical validation with ground truth for diagnostic or prognostic purposes, but rather controls basic device functions (e.g., suction settings, modes, battery indicators).

The performance testing listed in Section 9 ("Summary of Non-Clinical Performance Testing") includes:

• Vacuum level verification testing
• Backflow protection testing
• Use life testing
• Battery performance testing
• Battery status indicator testing

These are standard engineering and safety tests for a powered breast pump, not the type of studies typically conducted to evaluate AI/ML performance against acceptance criteria for a diagnostic or decision-support system.

In summary, the provided FDA 510(k) clearance letter and summary do not contain information related to AI/ML device performance or the study details requested in your prompt.

Ask a specific question about this device

K5 is intended to supply power to and serve as a base for dental devices and accessories. This product includes a dental chair. The dental treatment unit is intended for use in the dental clinic environment and is used by trained dentists and/or dental assistants.

A Dental Unit and Chair K5 is designed for dental treatment of children and adults. It is a dental treatment unit in accordance with IEC 80601-2-60. The 3-way syringe is a dental instrument in accordance with EN 1639. It aids the dental application in the mouth of the patient by supplying air, water or spray. This product is designed for use in dentistry only and may only be used by trained medical personnel. K5 is similar to other commercially available products based on the intended use, the technology used, the claims, the electrical power and performance characteristics. It is substantially equivalent in design, function and intended use to the predicate device.

The provided text describes a medical device, the K5, which is a dental operative unit and accessories, including a dental chair. It is a 510(k) submission to the FDA. However, the document does not contain acceptance criteria or a study that proves the device meets those criteria in the context of performance metrics like sensitivity, specificity, accuracy, or reader performance with or without AI assistance.

The document focuses on demonstrating substantial equivalence to a predicate device (K3, K183347) based on indications for use, technological characteristics, and compliance with various safety and performance standards.

Here's a breakdown of the requested information based on the provided text, highlighting where information is absent:

1. Table of Acceptance Criteria and Reported Device Performance

This information is not present in the document. The document discusses compliance with safety standards and functional equivalence to a predicate device, but it does not specify quantitative acceptance criteria for features like diagnostic accuracy, sensitivity, or specificity, nor does it provide a table of reported device performance against such criteria. The device is a dental operative unit, not an AI/diagnostic software, so these types of performance metrics are not applicable in this context.

2. Sample Size Used for the Test Set and Data Provenance

This information is not applicable in the context of AI/diagnostic software. The document describes non-clinical testing for areas like biocompatibility, cleaning validation, electrical safety, electromagnetic compatibility, and software verification/validation. These tests do not involve a "test set" of clinical data for performance evaluation in the way an AI algorithm would.

3. Number of Experts Used to Establish Ground Truth for the Test Set and Qualifications

This information is not applicable. The device is a dental operative unit, and its evaluation focuses on safety, functionality, and compliance with engineering standards, not on diagnostic performance or interpretation by experts to establish ground truth.

4. Adjudication Method for the Test Set

This information is not applicable. As there is no "test set" of clinical data for diagnostic performance requiring expert interpretation, no adjudication method is described.

5. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study Was Done

No, a multi-reader multi-case (MRMC) comparative effectiveness study was not done. This type of study is typically performed for diagnostic devices, particularly AI-powered ones, to assess how human readers' performance changes with AI assistance. The K5 is a dental operative unit, not a diagnostic AI tool.

6. If a Standalone (i.e., algorithm only without human-in-the-loop performance) Was Done

No, a standalone performance study in the context of an algorithm or AI was not done. The K5 is a physical dental unit with electronics and software for controlling its functions, not an AI algorithm intended for standalone performance evaluation in a diagnostic capacity.

7. The Type of Ground Truth Used

This information is not applicable in the context of diagnostic accuracy. The "ground truth" for the K5 device's evaluation is primarily based on:

• Compliance with recognized standards (e.g., IEC 60601-1 for electrical safety, ISO 10993-1 for biocompatibility).
• Functional performance (e.g., chair movement, fluid delivery, suction) as designed and tested against specifications.

8. The Sample Size for the Training Set

This information is not applicable. There is no mention of a "training set" in the context of machine learning or AI algorithms because the K5 is a dental operative unit, not an AI-driven diagnostic or analytical tool.

9. How the Ground Truth for the Training Set Was Established

This information is not applicable for the same reasons as point 8.

Ask a specific question about this device

The COSMED K5 Wearable Metabolic Technology is a device designed to measure cardio-respiratory and metabolic functions during stress testing, rehabilitation, sports medicine and other related activities, performed in professional healthcare facilities only. The system is not intended for Home Use.

The main measurements reported by the system are Oxygen Uptake production, Ventilation, Heart Rate and Energy Expenditure.

K5 is intended to use with adults and children over the age of 14 years.

It is to be used by physicians or by trained personnel on a physician responsibility.

The system and its accessories are indicated for the acquisition, analysis, formatting, display, printing and storage of certain physiologic signals. It must not be intended as a monitoring device, nor as a sole means for determining a patient's diagnosis but for the purpose of assisting the clinician in the diagnosis of cardio-pulmonary diseases

The COSMED K5 Wearable Metabolic Technology is a portable unit, designed for the measurement of resting and exercise metabolism in the laboratory, utilizing international measurement quidelines published by relevant scientific societies. The K5 consists of the following main parts:

• Main portable unit
• Optional Bluetooth receiver
• PC software
• Face mask with head cap
• Turbine flowmeter with optoelectronic reader and wind cover
• Harness
• Heart rate monitor belt
• 02 sensor
• Battery charger + batteries
• AC/DC adapter
• USB cable
• Carrying case
• Optional pressure regulator for calibration

The K5 system is intended to be used the laboratory, by either direct connection or by telemetry. The system offers both 'breath-by-breath' and 'mixing chamber' operational modes.

Here's an analysis of the acceptance criteria and study information for the COSMED K5 Wearable Metabolic Technology, based on the provided FDA 510(k) summary:

Note: The provided document is an FDA 510(k) summary, which focuses on demonstrating substantial equivalence to a predicate device rather than providing a detailed clinical study report. Therefore, some of the requested information, particularly regarding specific study details like training set provenance, expert qualifications, and detailed statistical methodologies for clinical trials, is not fully elaborated in this type of document.

1. Table of Acceptance Criteria and Reported Device Performance

The document mentions "Accuracy validation (Vt, RF, VO2, VCO2)" as a non-clinical test. The table on page 7 provides specific measurement accuracies for ventilation, VO2, and VCO2, which serve as the acceptance criteria and reported performance.

Ask a specific question about this device

The ETOH method is an in-vitro diagnostic test for the quantitative measurement of ethyl alcohol in human serum, plasma and urine. Ethyl alcohol test results may be used in the diagnosis and treatment of alcohol intoxication and poisoning.

The Dimension Vista® ETOH Flex® reagent cartridge is a prepackaged in-vitro diagnostic test method that is specifically designed to be used on the Dade Behring Dimension Vista® System. The reagents contained in the Dimension Vista® ETOH Flex® reagent cartridge are: Reagent 1 which contains the buffering system and; Reagent 2 which contains alcohol dehydrogenase (ADH), the coenzyme nicotinamide adenine dinucleotide (NAD), buffer, preservatives, and stabilizers.

The provided text describes a 510(k) submission for the Dimension Vista® Ethyl Alcohol (ETOH) Flex® Reagent Cartridge. This document is focused on establishing substantial equivalence to predicate devices rather than proving the device meets specific acceptance criteria through a standalone study with defined performance metrics as might be found in an AI/ML device submission.

Therefore, many of the requested elements for an AI/ML device study, such as sample sizes for test sets, data provenance, number and qualifications of experts, adjudication methods, MRMC studies, standalone performance, and training set details, are not applicable to this type of submission.

Here's a breakdown of what can be extracted based on the provided text:

1. A table of acceptance criteria and the reported device performance:

The document doesn't explicitly state "acceptance criteria" in the way an AI/ML device study would. Instead, it demonstrates performance by comparing its features and principles to predicate devices and stating that comparative testing demonstrates substantial equivalent performance. Without specific thresholds or numerical acceptance criteria for performance metrics (e.g., accuracy, sensitivity, specificity), a direct comparison table as requested cannot be fully generated.

However, we can infer "performance" from the comparison to predicate devices, focusing on areas like measuring range, sample type, and principle.

2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective):

• Sample Size: Not specified. The document states "Comparative testing described in the protocol included in this submission demonstrates substantial equivalent performance," but does not detail the number of samples or cases used in this testing.
• Data Provenance: Not specified.

3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience):

Not applicable. This is a chemical assay, and "ground truth" would be established through reference methods or validated laboratory results, not expert consensus in the diagnostic imaging sense.

4. Adjudication method (e.g. 2+1, 3+1, none) for the test set:

Not applicable. As a chemical assay, adjudication methods are not relevant.

5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance:

Not applicable. This is a laboratory diagnostic assay, not an AI-assisted diagnostic imaging device that involves human readers.

6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done:

Not applicable in the AI/ML sense. This device is a reagent cartridge for an automated analyzer. Its performance is standalone in that it directly measures ethyl alcohol concentrations. However, this is not an "algorithm-only" performance as traditionally understood for AI/ML devices.

7. The type of ground truth used (expert consensus, pathology, outcomes data, etc):

The ground truth for a chemical assay like this would typically be established using reference methods or highly accurate analytical techniques for ethyl alcohol concentration. The document does not explicitly state the specific reference method used but implies that the performance was compared to established predicate devices and internal validation protocols.

8. The sample size for the training set:

Not applicable. This is a chemical reagent cartridge, not a machine learning model that undergoes a "training phase" in the conventional sense. Its development relies on chemical and biological principles and optimization, not data-driven training as in AI/ML.

9. How the ground truth for the training set was established:

Not applicable, as there is no "training set" in the AI/ML context for this device.

Ask a specific question about this device

Replacement battery pack for SHERWOOD 224, 324 FEEDING PUMP & SHERWOOD K524 INTRI-FLUSH This battery will be shipped to biomedical equipment technicians and or customers who request a replacement battery for the particular device(s) listed above

Replacement battery pack for SHERWOOD 224, 324 FEEDING PUMP & SHERWOOD K524 INTRI-FLUSH

This document is a 510(k) premarket notification approval letter for a replacement battery pack. It does not contain information about acceptance criteria or a study proving that a device meets such criteria. Therefore, I cannot generate the requested information based on the provided text.

Ask a specific question about this device

The Multifunction KEITO K5 is intended to be used by adults in order to measure height, weight, systolic and diastolic blood pressures, and to calculate pulse rate.

The Multifunction KEITO K5 (K5) is designed to provide the user with measurements of blood pressure, height, and weight, as well as to calculate the Body Mass Index (BMI) and pulse rate. The user is prompted to select a measurement cycle, step onto the K5 platform, and wait momentarily while the measurements and calculations are performed. After the measurements have been taken, the K5 provides the user with the results. To operate the K5 the user inserts a coin into the coin slot, and steps onto the platform. The user has the option of selecting a partial measuring cycle or a complete cycle. In a partial cycle, weight and height measurements are taken and Body Mass Index calculations are performed in the partial cycle. In a complete cycle, weight, height, blood pressure, and pulse measurements are taken. Body Mass Index is calculated and the W.H.O. blood pressure recommendations are provided. The K5 prints out a ticket containing the results of the measurements and the recommended ranges for both BMI and blood pressure.

Here's an analysis of the acceptance criteria and study information for the Multifunction KEITO K5, based on the provided document:

1. Acceptance Criteria and Reported Device Performance

2. Sample Size and Data Provenance for Test Set

• Blood Pressure Accuracy Test:
  • Sample Size: Not explicitly stated, but the test compared the K5 to a manual sphygmomanometer.
  • Data Provenance: The testing was conducted by Physikalisch-Technische Bundesanstalt (a German national metrology institute), implying the data was collected in Germany. It is implied to be prospective testing for regulatory approval.
• Height Compensation Test:
  • Sample Size: "multiple users of different heights, ages and sex." The exact number is not specified.
  • Data Provenance: Not explicitly stated, but likely conducted by the manufacturer or a third-party testing facility. It is implied to be prospective.

3. Number of Experts and Qualifications for Ground Truth (Test Set)

• Blood Pressure Accuracy Test:
  • The "ground truth" was established by a manual sphygmomanometer, which is the gold standard for clinical blood pressure measurement.
  • The document does not specify the number or qualifications of clinicians/technicians operating the manual sphygmomanometer, but it's implied they were trained professionals given the regulatory context.
• Height Compensation Test:
  • The ground truth for blood pressure measurements in this test would also be the manual sphygmomanometer.
  • No specific experts mentioned for validating the compensatory formula itself, beyond the statistical methodologies applied.

4. Adjudication Method for the Test Set

• No specific adjudication method (like 2+1, 3+1 consensus) is described.
• For the blood pressure accuracy, the comparison was directly between the device and the manual sphygmomanometer, with results being "evaluated in accordance with the acceptance requirements of the regulation." This suggests a direct comparison against a standard rather than expert adjudication of AI outputs.

5. Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study

• No MRMC comparative effectiveness study was mentioned. The device is a standalone measurement system, not an AI assisting human readers.

6. Standalone Performance Study

• Yes, a standalone performance study was done.
  • The pressure system of the Multifunction KEITO K5 was tested by Physikalisch-Technische Bundesanstalt to verify its accuracy against a manual sphygmomanometer.
  • Additional testing was conducted on the K5 to determine correct user height compensation.

7. Type of Ground Truth Used (Test Set)

• Blood Pressure Accuracy Test: Comparison against a gold standard (manual sphygmomanometer).
• Height Compensation Test: Comparison against a gold standard (manual sphygmomanometer), along with objective measurements of height, age, and sex.

8. Sample Size for the Training Set

• The document does not explicitly describe a "training set" in the context of an AI/machine learning model. The K5 is described as a non-invasive blood pressure measurement system, not an AI-driven diagnostic or image analysis tool that would typically have a distinct training set.
• The "formula was developed to compensate for user height" based on testing "multiple users of different heights, ages and sex." This process of developing the formula might be considered analogous to a training phase, but the sample size is not specified beyond "multiple users."

9. How the Ground Truth for the Training Set was Established

• As above, the concept of a "training set" for an AI model isn't directly applicable here.
• If we consider the development of the height compensation formula as an analogous process, the "ground truth" for developing this formula was established by using manual sphygmomanometer readings and objective user height measurements from "multiple users of different heights, ages and sex." The formula was then derived using "statistical methodologies" to correlate these measurements and compensate for variations.

Ask a specific question about this device